# Back-and-Forth prediction for deep tensor compression

arXiv: https://arxiv.org/abs/2002.07036 · HTML: https://mlsanity.com/paper/2002.07036/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2020.

## Built on by (most cited first, 16 of 16)

- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [Lightweight compression of neural network feature tensors for collaborative intelligence](https://mlsanity.com/paper/2105.06002/) (2021)
- [SC2 Benchmark: Supervised Compression for Split Computing](https://mlsanity.com/paper/2203.08875/) (2022)
- [Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics](https://mlsanity.com/paper/2110.09241/) (2021)
- [C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication-Efficient Split Learning](https://mlsanity.com/paper/2207.12397/) (2022)
- [Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence](https://mlsanity.com/paper/2105.07102/) (2021)
- [Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation](https://mlsanity.com/paper/2105.00591/) (2021)
- [High Efficiency Image Compression for Large Visual-Language Models](https://mlsanity.com/paper/2407.17060/) (2024)
- [Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems](https://mlsanity.com/paper/2306.12691/) (2023)
- [On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance](https://mlsanity.com/paper/2403.17154/) (2024)
- [Ampere: Communication-Efficient and High-Accuracy Split Federated Learning](https://mlsanity.com/paper/2507.07130/) (2025)
- [Emerging Standards for Machine-to-Machine Video Coding](https://mlsanity.com/paper/2512.10230/) (2025)
- [LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks](https://mlsanity.com/paper/2504.13736/) (2025)
- [Latent-Space Inpainting for Packet Loss Concealment in Collaborative Object Detection](https://mlsanity.com/paper/2102.00142/) (2021)
- [Analysis of Latent-Space Motion for Collaborative Intelligence](https://mlsanity.com/paper/2102.04018/) (2021)
- [DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels](https://mlsanity.com/paper/2112.00794/) (2021)

## Abstract (arXiv)

Recent AI applications such as Collaborative Intelligence with neural networks involve transferring deep feature tensors between various computing devices. This necessitates tensor compression in order to optimize the usage of bandwidth-constrained channels between devices. In this paper we present a prediction scheme called Back-and-Forth (BaF) prediction, developed for deep feature tensors, which allows us to dramatically reduce tensor size and improve its compressibility. Our experiments with a state-of-the-art object detector demonstrate that the proposed method allows us to significantly reduce the number of bits needed for compressing feature tensors extracted from deep within the model, with negligible degradation of the detection performance and without requiring any retraining of the network weights. We achieve a 62% and 75% reduction in tensor size while keeping the loss in accuracy of the network to less than 1% and 2%, respectively.